Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.9517. Min Act: -0.0000

Data Index: 785968 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.9983. Min Act: -0.0000

Data Index: 421404 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.9075. Min Act: -0.0000

Data Index: 499332 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1323654 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8794. Min Act: -0.0000

Data Index: 193152 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8736. Min Act: -0.0000

Data Index: 31372 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8577. Min Act: -0.0000

Data Index: 287711 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8579. Min Act: -0.0000

Data Index: 912646 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8144. Min Act: -0.0000

Data Index: 629195 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1178501 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1055134 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7894. Min Act: -0.0000

Data Index: 14618 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1167523 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.8080. Min Act: -0.0001

Data Index: 55744 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7954. Min Act: -0.0000

Data Index: 568734 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7713. Min Act: -0.0000

Data Index: 414898 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.6353. Min Act: -0.0001

Data Index: 26347 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1071546 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7975. Min Act: -0.0000

Data Index: 753051 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.9983. Min Range: -0.9983

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1093196 (C4 (Web Text))

Max Activating Token Index: 971